Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    ANY

    np_max-act · gemini-2.0-flash

    The neuron fires on the word “THEORY” as it appears in “theory of liability” clauses in software license headers.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    cancellationToken
    -0.07
    ώς
    -0.07
    \Log
    -0.07
    هور
    -0.07
    uing
    -0.06
    olut
    -0.06
    zeigt
    -0.06
    ridden
    -0.06
    017
    -0.06
    ８
    -0.06
    POSITIVE LOGITS
    .getModel
    0.06
     Estate
    0.06
    Nobody
    0.06
    าศาสตร
    0.06
    	copy
    0.06
    =='
    0.06
     yak
    0.06
     приобрет
    0.06
    ITICAL
    0.06
     ตำ
    0.06
    Act Density 0.001%

    No Known Activations